CN115375205A - Method, device and equipment for determining water user portrait - Google Patents
Method, device and equipment for determining water user portrait Download PDFInfo
- Publication number
- CN115375205A CN115375205A CN202211307492.XA CN202211307492A CN115375205A CN 115375205 A CN115375205 A CN 115375205A CN 202211307492 A CN202211307492 A CN 202211307492A CN 115375205 A CN115375205 A CN 115375205A
- Authority
- CN
- China
- Prior art keywords
- data information
- water
- historical data
- user
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012545 processing Methods 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000007418 data mining Methods 0.000 claims description 21
- 230000008929 regeneration Effects 0.000 claims description 6
- 238000011069 regeneration method Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 239000002131 composite material Substances 0.000 claims description 4
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 238000012549 training Methods 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000009172 bursting Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device and equipment for determining a water user portrait. Wherein the method comprises the following steps: acquiring historical data information of at least one water using user; determining at least one type of label corresponding to the historical data information according to the historical data information; acquiring current data information of at least one water user, and determining a target label corresponding to the current data information in the at least one type of label; determining a water user portrait according to the target label; wherein the data information comprises at least one of basic information, water consumption information, payment information and service information. The scheme of the invention can comprehensively and specifically describe the characteristics of the users, realize scientific scheduling of the water supply system and improve the water supply efficiency.
Description
Technical Field
The invention relates to the technical field of computer information processing, in particular to a method, a device and equipment for determining a water user portrait.
Background
The water consumption is closely related to the life of people, and the water consumption behavior of users is influenced by various factors, such as the number of families, the personnel structure, the external temperature, the water consumption habit and the like; when data such as massive user water consumption and payment are counted, the counting efficiency is low, water supply is difficult to perform according to specific conditions of users, and the water supply efficiency is low.
Disclosure of Invention
The invention provides a method, a device and equipment for determining a water user portrait, which can comprehensively and specifically describe user characteristics, realize scientific scheduling of a water supply system and improve water supply efficiency.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a method of determining a water user profile, the method comprising:
acquiring historical data information of at least one water using user;
determining at least one type of label corresponding to the historical data information according to the historical data information;
acquiring current data information of at least one water user, and determining a target label corresponding to the current data information in the at least one type of label;
determining a water user portrait according to the target label;
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
Optionally, the at least one type of tag includes:
counting class labels;
a rule class label;
a data mining class tag.
Optionally, when the tag is a statistical tag, determining at least one type of tag corresponding to the historical data information according to the historical data information, including:
and adding a statistical class label corresponding to the historical data information for the historical data information.
Optionally, when the tag is a rule-class tag, determining at least one class of tag corresponding to the historical data information according to the historical data information, including:
calculating through a first preset algorithm according to the historical data information to obtain a first calculation result;
and comparing the first calculation result with a preset rule to obtain a rule class label corresponding to the historical data information.
Optionally, when the tag is a data mining type tag, determining at least one type of tag corresponding to the historical data information according to the historical data information, including:
calculating through a second preset algorithm according to the historical data information to obtain a second calculation result;
and clustering the second calculation result to obtain a data mining class label corresponding to the historical data information.
Optionally, the method for determining a user profile with water further includes:
and preprocessing the historical data information to obtain the processed historical data information.
Optionally, the method for determining a user profile with water further includes:
and performing at least one of cross processing, nesting processing, association processing and/or regeneration processing on the target label to obtain a composite target label.
The invention also provides a water user profile determination apparatus, said apparatus comprising:
the acquisition module is used for acquiring historical data information of at least one water using user;
the processing module is used for determining at least one type of label corresponding to the historical data information according to the historical data information;
the acquisition module is further configured to acquire current data information of at least one water user, and determine a target tag corresponding to the current data information in the at least one type of tag;
the processing module is further used for determining the water user portrait according to the target label;
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
The present invention also provides a computing device comprising: a processor, a memory and a program or instructions stored on the memory and executable on the processor, which when executed by the processor, implement the steps of the method as described above.
The invention also provides a readable storage medium on which a program or instructions are stored which, when executed by a processor, implement the steps of the method as described above.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, historical data information of at least one water user is obtained; determining at least one type of label corresponding to the historical data information according to the historical data information; acquiring current data information of at least one water user, and determining a target label corresponding to the current data information in the at least one type of label; determining a water user portrait according to the target label; wherein the data information comprises at least one of basic information, water consumption information, payment information and service information. The user characteristics can be comprehensively and specifically described, scientific scheduling of a water supply system is realized, and the water supply efficiency is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for determining a user profile of a water user according to an embodiment of the present invention;
FIG. 2 is a block diagram of a water user representation determination apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in FIG. 1, an embodiment of the present invention provides a method for determining a water user profile, the method comprising:
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
Wherein the basic information may include, but is not limited to: information such as user file data, water meter file data and the like; specifically, the method may include but is not limited to: information such as a water user number, a cell position, whether secondary water supply exists, a house area, a population number, a water meter type, water meter installation time and/or water meter service life;
the water usage information may include, but is not limited to: data of meter reading, data of intelligent water meter, water pressure data and the like; specifically, the method may include but is not limited to: the last time of reading, the reading period, the water consumption and/or the water consumption step and other information; the intelligent water meter can acquire the water consumption condition of a user in real time and can acquire a long-period water consumption data historical record; the water pressure data can be directly obtained by adopting an intelligent water meter, and if the water pressure data cannot be obtained by adopting a common water meter, the water pressure data can be obtained by taking an approximate value of the water pressure data of the pump station;
the payment data may include, but is not limited to: information such as charging data, payment data, arrearage data and the like; specifically, the method may include but is not limited to: the information of the fee due to meter reading or the fee due to charge, the bill output time, the fee payment period (the fee payment time-the bill time), the fee payment mode, the arrearage amount, the arrearage times, the arrearage frequency, the timeliness of fee payment, the accumulated arrearage amount, the collection times and/or the collection urging record and the like directly obtained by the intelligent water meter;
the service information may include, but is not limited to: the information such as installation data, service work order data, hot line data, water cut-off data and the like is reported; specifically, the method may include but is not limited to: average water cut-off duration, water cut-off times, planned water cut-off and water supply timeliness, planned water cut-off notification timeliness and/or water cut-off reason and other information;
in addition, the service information can also be associated with information such as pipe bursting information and engineering construction, and the time and the place in the pipe bursting information and the engineering construction information can be associated with the affected water users.
In the embodiment of the invention, the user characteristics can be comprehensively and specifically described by constructing the water user portrait for the water users, thereby realizing scientific dispatching of the water supply system and improving the water supply efficiency.
The water user image is labeled by water user information, and can provide a sufficient information basis for water supply enterprises and help the water supply enterprises to quickly find information such as water user requirements; the user portrait of the water consumption is determined, personalized service can be provided for the user, the water consumption experience of the user is improved, and the water consumption law of a large number of water consumption users can provide guidance for reasonable water supply, so that the water supply efficiency is improved.
In an optional embodiment of the present invention, in step 12, the at least one type of tag includes:
counting class labels;
a rule class label;
a data mining class tag.
It should be noted that the statistics class tag, the rules class tag, and the data mining class tag may specifically include, but are not limited to: basic labels, security labels, violation labels, cooperation labels and public opinion labels;
wherein the base tags may include, but are not limited to: a water consumption grade label, a water consumption fluctuation grade label, a community grade label, a user age group label and the like;
the security tag may include, but is not limited to: accident frequency labels, accident severity labels, etc.;
the violation tags may include, but are not limited to: a violation water use frequency label, an arrearage reason label and the like;
the collaboration tags may include, but are not limited to: hot line type tags, hot line frequency tags, etc.;
the public opinion tags may include, but are not limited to: public opinion grade, public opinion frequency labels, etc.
In this embodiment, the statistics type tag, the rules type tag and the data mining type tag can be specifically divided into a plurality of tags, and the characteristics of the client can be described in more detail, so that the client condition can be accurately locked, and accurate water supply can be performed.
In another optional embodiment of the present invention, when the tag is a statistical-type tag, the step 12 may include:
and step 121, adding a statistical class label corresponding to the historical data information.
In this embodiment, for a single water user, the natural attributes and table basic attributes of the user may be counted, and the natural attributes of the user include, but are not limited to: user name, address, water consumption in nearly one month, step water cost, etc.; table base attributes include, but are not limited to: the method comprises the following steps of (1) measuring the number, the type, the signal, the voltage of a battery, the reporting period, the state of a valve and the like; for example: the account opening date of the user, the address of the user, the payment times of 30 days, the payment amount of the last half year and the like.
Specifically, taking the payment times of the near 30 days as an example, the first-level classification tag corresponding to the payment times of the near 30 days is used as a cost statistic, and the detailed description of the tag corresponding to the payment times of the near 30 days may include: and simultaneously, recording and updating in the service system, and extracting metadata from the data warehouse at regular time for analysis, so that the payment information of the user is kept in the latest state.
In another optional embodiment of the present invention, when the label is a rule-class label, the step 12 may include:
step 122, calculating through a first preset algorithm according to the historical data information to obtain a first calculation result;
and step 123, comparing the first calculation result with a preset rule to obtain a rule class label corresponding to the historical data information.
In this embodiment, the rule-class labels may be various labels generated by a screening rule determined based on water consumption behaviors of water service operation and maintenance personnel to users, state sensing information corresponding to water meter types, metering information, time information, and the like.
Wherein the preset rules may include, but are not limited to: predetermined numbers or ranges, for example: presetting three rules for the arrearage amount label, which are respectively as follows: the user accumulated arrearage is less than 1000 yuan in last two years, the user accumulated arrearage is more than 1 ten thousand yuan and less than 2 ten thousand yuan in last two years, and the user accumulated arrearage is more than 2 ten thousand yuan in last two years, if the first calculation result accords with that the user accumulated arrearage is less than 1000 yuan in last two years, the user corresponds to the small-amount user label; if the first calculation result conforms to the condition that the accumulated arrearage of the user is more than 1 ten thousand yuan and less than 2 ten thousand yuan in the last two years, the user corresponds to a high-fund user tag; and if the first calculation result conforms to that the accumulated arrearage of the user is more than 2 ten thousand yuan in the last two years, the user corresponds to the super-large-amount user label.
The first preset algorithm may include, but is not limited to: calculating statistics of the data information, which may include but is not limited to: mean, median, percentile, etc., for example: the payment timeliness data can be based on the average value of the payment periods of all the users, (the payment period = payment time-billing time), the user with the payment period lower than the average value corresponds to the positive payment tag, the user with the payment period higher than the average value corresponds to the negative payment tag, and the user with the payment period empty corresponds to the delinquent payment tag for the last time the bill is paid but no payment record is recorded.
In an optional specific embodiment of the present invention, the process of calculating the accumulated amount of owed fees of the first user in the last two years by using a first preset algorithm and determining the label corresponding to the first user may specifically include:
setting a preset value as-100 yuan, subtracting the accumulated due payment amount of the first user in the last two years from the accumulated payment amount of the first user in the last two years to obtain the accumulated arrearage amount of the first user in the last two years, comparing the obtained accumulated arrearage amount of the first user in the last two years with a preset threshold, and if the accumulated arrearage amount of the first user in the last two years is greater than the preset threshold, enabling the first user to correspond to the negative payment label; if the accumulated amount of the arrearage of the first user in the last two years is equal to the preset threshold, the first user corresponds to the normal payment label; and if the accumulated amount of the arrearage of the first user in the last two years is smaller than the preset threshold value, the first user corresponds to the active payment label.
Specifically, the accumulated amount of the first user in the last two years is 500 yuan, and the accumulated amount of the first user to be paid in the last two years is 800 yuan, so that the accumulated amount of the first user in the last two years is-300 yuan, and the accumulated amount of the first user in the last two years is compared with a preset threshold value-100 yuan, and it is determined that the accumulated amount of the first user in the last two years is greater than the preset threshold value, and then the first user corresponds to the passive payment tag.
In another optional embodiment of the present invention, when the tag is a data mining class tag, the step 12 may include:
step 124, calculating according to the historical data information through a second preset algorithm to obtain a second calculation result;
and step 125, clustering the second calculation result to obtain a data mining class label corresponding to the historical data information.
It should be noted that, for achieving the purpose of the present invention, the step of obtaining the second calculation result by performing the calculation through the second preset algorithm is not necessary, and the data mining class label corresponding to the historical data information may also be obtained by directly performing the cluster analysis on the historical data information and/or the first calculation result obtained through the first preset algorithm. In this embodiment, the second preset algorithm may include a prediction algorithm based on historical data information. For example, based on the historical water consumption data of the target user for the last three years, a prediction algorithm is used to predict the water consumption of the target user in the next month, and the prediction algorithm may include but is not limited to: LSTM (long short term memory artificial neural network), SVM (support vector machine), XGBoost (distributed gradient enhanced library), and the like;
the second preset algorithm may further include a comparison of the user data information with historical data information. For example, by means of data mining, the water consumption is compared with the historical water consumption, and when the water consumption of a user in a certain time period is found to be significantly higher than the average historical level, the abnormal water consumption phenomenon is prompted, and water leakage and other phenomena are possible to occur. The accurate description of the water consumption condition of the water consumption user can be realized, and accurate water supply is facilitated.
In another optional specific embodiment of the present invention, when the second preset algorithm is XGBoost, the process of determining the data mining class tag corresponding to the historical data information may specifically include:
acquiring historical water consumption data of a target user in three years by taking one month as a unit, wherein the historical water consumption data of each month is processed by an interpolation method for the historical water consumption data of which the statistical period is more than one month; randomly dividing historical water consumption data into 80% of training set and 20% of verification set;
inputting the training set into the XGboost prediction model, wherein a set formed by training k regression trees by an XGboost algorithm is as follows: f = { F1 (X), F2 (X), \8230;, fk-1 (X) };
fitting the (c-1) th regression tree through the (c) th regression tree, calculating to obtain a residual error, and adding the predicted values of all the regression trees to obtain a final prediction result, wherein the training iteration result of the (t) th time is calculated according to the following formula:
wherein the content of the first and second substances,
for the result of the t-th training iteration,
for the result of the t-1 st training iteration,
predicting the value of the ith sample in the Kth regression tree;
when a sample x is given, the prediction result for the sample is the sum of the predicted values of each tree, wherein the user water consumption XGBoost prediction model is as follows:
wherein, the first and the second end of the pipe are connected with each other,
the water consumption is predicted for the user,
is the predicted value of the Kth regression tree, K is the total number of the regression trees,
the predicted value of the ith sample in the Kth tree; f is a set formed by k regression trees;
the XGboost prediction model has the following objective function:
wherein, the first and the second end of the pipe are connected with each other,
for the objective function of the XGBoost prediction model,
the real value of the water consumption is provided for the user,
as a result of a previous prediction，
The residual calculated for the t-th training,
the method comprises the following steps of taking a loss function of a prediction model, wherein n is the total number of samples, i is the ith sample, t is the training times, and k is the number of regression trees;
wherein, the first and the second end of the pipe are connected with each other,
is a loss function of the predictive model,
is the penalty coefficient of the regression tree leaf node,
in order to regress the number of the leaf nodes,
is the weight value of the regression tree leaf node,
regularization coefficients which are regression leaf node weights;
the objective function of the prediction model can be expanded by a Taylor series, and the calculation formula is as follows:
wherein the content of the first and second substances,
is the first derivative of the loss function,
is the second derivative of the loss function;
the accuracy of the verification model of the verification data set is determined by using a user water consumption prediction model established based on an XGboost prediction model, and the calculation formula of the root mean square error used for the estimation of the prediction model is as follows:
wherein RMSE is the root mean square error of the prediction model,
the predicted value of the water consumption for the user,
the actual value of water consumption for the user;
parameters of the decision tree are adjusted and optimized through continuous training, and after the parameters are adjusted and optimized, XGboost regularization parameters are adjusted and optimized to reduce the complexity of the model and improve the model performance; and finally, determining an ideal parameter combination as the parameters of the XGboost prediction model.
In another optional embodiment of the present invention, the process of directly clustering the data information to obtain the data mining class label corresponding to the data information may specifically include:
dividing user water consumption data of the intelligent water meter into seven sections of data corresponding to 1-7 days from Monday to Sunday according to 24-hour system, and dividing the data of 7 days according to 12 time periods respectively, and recording as: q t1 ,Q t2 ,……,Q t12 At 0 ofTaking a point as a starting point, dividing every two hours as a time period, namely: q t1 ：0:00-2:00，Q t2 ：2:00-4:00,……，Q t11 ：20:00-22:00，Q t12 :22:00-24:00. And subtracting the water consumption value of the starting time node from the water consumption value of the ending time node of each time period to obtain the water consumption of each time period.
Selecting three typical time periods of morning, noon and evening for analysis, for example, taking the average water consumption of the three time periods of 6-8; and labeling different users of K types as different data mining type labels according to the water consumption characteristics of the users, such as: the water consumption of the user a is characterized in that the water consumption of the user a in the morning and at night is two peaks, the water consumption of the user a in the noon is zero or far lower than the water consumption of the user a in the morning and at night, and the user a corresponds to a conventional office resident label; and the water consumption characteristic of the user b is that the difference of the water consumption in the morning, the noon and the evening is not large, and the user b corresponds to the label of the perennial household residents.
Under the condition that a large amount of historical data information exists after the system runs stably in the process of depicting the water user portrait, various types of data are collected, data mining is carried out by using methods such as machine learning, clustering analysis is carried out on the user, and therefore the change trend of macroscopic data can be counted through data mining labels, for example: whether the meter used by the water service user is an abnormal data meter or not, whether water leakage exists in the water used by the user or not and the like.
For example: in the statistical analysis of the user's cumulative water usage and water usage trends, clustering algorithms can be used, which can include, but are not limited to: K-Means (K-Means clustering algorithm), mean Shift (Mean Shift), DBSCAN (density-based clustering algorithm), etc.,
the Mean Shift has the following calculation formula of Mean center:
wherein the content of the first and second substances,
the calculated center of the cluster is represented,
a data point representing the current calculation is represented,
representing the ith sample point in the data set,
the weight of the ith sample point is represented,
which represents the number of sample points that are,
a representation kernel function, an optional gaussian kernel, etc.
Therefore, the sample set can be divided into a plurality of cluster clusters according to the distance between samples corresponding to the given water meter user sample set, the distance between points in the cluster clusters is made to be as small as possible, the distance between the cluster clusters is made to be as large as possible, the cluster clusters are finally distinguished through repeated regression clustering of the user, and the characteristics of each cluster are described through data characteristics.
Specifically, for the user who uses intelligent water gauge, because can accurate statistics user's water consumption, can learn the water consumption of every day even every hour, consequently can classify water user's water characteristics, classify according to water user's water characteristics, according to water user's water information, the water consumption of every hour in every day to and the water consumption change of weekday and weekend, can apply clustering algorithm to carry out automatic classification, form corresponding data mining class label.
In another optional embodiment of the present invention, after the step 11, the method may further include:
and 11-1, preprocessing the historical data information to obtain the processed historical data information.
In this embodiment, the preprocessing the historical data information may include, but is not limited to: cleaning, feature extraction and/or data analysis of the data, for example: and eliminating data with zero in the historical data information, and the like. Therefore, the interference of abnormal data can be avoided, and the user portrait can be more accurate.
In another optional embodiment of the present invention, the method for determining a user profile with water may further include:
and step 15, performing at least one of cross processing, nesting processing, association processing and/or regeneration processing on the target label to obtain a composite target label.
In this embodiment, a tag that better meets the actual service requirement can be formed by at least one of cross processing, nesting processing, association processing, and/or regeneration processing on the target tag;
the cross-processing of the target tag may include: combining a plurality of labels into one label with multiple attributes;
the nesting process for the target tag may include: arranging and binding a plurality of labels with subordination relation according to the thinning degree of the labels so as to adapt to different requirements on portrait precision;
the association processing of the target tag may include: and binding the labels belonging to the same user or the same application.
The regeneration process of the target tag may include: when the currently matched label cannot solve the specific problem in reality, adjusting the data in the data source or regenerating the label.
In the embodiment of the invention, the label can be defined based on the service data such as the basic information, the water consumption information and/or the service information of the water consumption user as the guidance, and the constructed water consumption user portrait can describe the characteristics of the water consumption user more comprehensively and in detail, so that the water consumption and the payment condition of the water consumption user can be analyzed and predicted, the scientific scheduling of a water supply system can be better guided, the water supply efficiency is improved, and the water charge payment rate is provided.
As shown in FIG. 2, embodiments of the present invention also provide a water user representation determination apparatus 20, said apparatus 20 comprising:
the acquisition module 21 is used for acquiring historical data information of at least one water using user;
the processing module 22 is configured to determine at least one type of tag corresponding to the historical data information according to the historical data information;
the acquisition module is further configured to acquire current data information of at least one water user, and determine a target tag corresponding to the current data information in the at least one type of tag;
the processing module is further used for determining the water user portrait according to the target label;
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
Optionally, the at least one type of tag includes:
counting class labels;
a rule class label;
a data mining class tag.
Optionally, when the tag is a statistical tag, determining at least one type of tag corresponding to the historical data information according to the historical data information, including:
and adding a statistical class label corresponding to the historical data information for the historical data information.
Optionally, when the tag is a rule-class tag, determining at least one class of tag corresponding to the historical data information according to the historical data information, where the determining includes:
calculating through a first preset algorithm according to the historical data information to obtain a first calculation result;
and comparing the first calculation result with a preset rule to obtain a rule class label corresponding to the historical data information.
Optionally, when the tag is a data mining-type tag, determining at least one type of tag corresponding to the historical data information according to the historical data information and the historical data information, including:
calculating through a second preset algorithm according to the historical data information to obtain a second calculation result;
and clustering the second calculation result to obtain a data mining class label corresponding to the historical data information.
Optionally, the processing module 22 may be further configured to:
and preprocessing the historical data information to obtain the processed historical data information.
Optionally, the processing module 22 may be further configured to:
and performing at least one of cross processing, nesting processing, association processing and/or regeneration processing on the target label to obtain a composite target label.
It should be noted that the apparatus is an apparatus corresponding to the method, and all implementation manners in the method embodiments are applicable to the embodiment of the apparatus, and the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device, comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the above method embodiment are applicable to this embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method as described above. All the implementation manners in the above method embodiment are applicable to this embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
Furthermore, it is to be noted that in the device and method of the invention, it is obvious that the individual components or steps can be decomposed and/or recombined. These decompositions and/or recombinations are to be regarded as equivalents of the present invention. Also, the steps of performing the series of processes described above may naturally be performed chronologically in the order described, but need not necessarily be performed chronologically, and some steps may be performed in parallel or independently of each other. It will be understood by those skilled in the art that all or any of the steps or elements of the method and apparatus of the present invention may be implemented in any computing device (including processor, storage medium, etc.) or network of computing devices, in hardware, firmware, software, or any combination thereof, which can be implemented by those skilled in the art using their basic programming skills after reading the description of the present invention.
The object of the invention is thus also achieved by a program or a set of programs running on any computing device. The computing device may be a general purpose device as is well known. The object of the invention is thus also achieved solely by providing a program product comprising program code for implementing the method or the apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is to be understood that the storage medium may be any known storage medium or any storage medium developed in the future. It is further noted that in the apparatus and method of the present invention, it is apparent that each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present invention. Also, the steps of executing the series of processes described above may naturally be executed chronologically in the order described, but need not necessarily be executed chronologically. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A method for determining a user profile for water use, the method comprising:
acquiring historical data information of at least one water using user;
determining at least one type of label corresponding to the historical data information according to the historical data information;
acquiring current data information of at least one water user, and determining a target label corresponding to the current data information in the at least one type of label;
determining a water user portrait according to the target label;
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
2. The method of claim 1, wherein the at least one type of tag comprises:
counting class labels;
a rule class label;
a data mining class tag.
3. The method for determining a user profile of water users as claimed in claim 2, wherein when the tag is a statistical tag, determining at least one type of tag corresponding to the historical data information according to the historical data information comprises:
and adding a statistical class label corresponding to the historical data information for the historical data information.
4. The method for determining a user profile of water users as claimed in claim 2, wherein when the tag is a rule-based tag, determining at least one type of tag corresponding to the historical data information according to the historical data information comprises:
calculating through a first preset algorithm according to the historical data information to obtain a first calculation result;
and comparing the first calculation result with a preset rule to obtain a rule class label corresponding to the historical data information.
5. The method for determining a user figure as claimed in claim 2, wherein when the tag is a data mining tag, determining at least one type of tag corresponding to the historical data information according to the historical data information comprises:
calculating through a second preset algorithm according to the historical data information to obtain a second calculation result;
and clustering the second calculation result to obtain a data mining class label corresponding to the historical data information.
6. The method of claim 1, further comprising:
and preprocessing the historical data information to obtain the processed historical data information.
7. The method for determining a user profile with water of claim 1, further comprising:
and performing at least one of cross processing, nesting processing, association processing and/or regeneration processing on the target label to obtain a composite target label.
8. A water user representation determining apparatus, said apparatus comprising:
the acquisition module is used for acquiring historical data information of at least one water user;
the processing module is used for determining at least one type of label corresponding to the historical data information according to the historical data information;
the acquisition module is further used for acquiring current data information of at least one water user, and determining a target label corresponding to the current data information in the at least one type of label;
the processing module is further used for determining the water user portrait according to the target label;
wherein the data information comprises at least one of basic information, water consumption information, payment information and service information.
9. A computing device, comprising: a processor, a memory and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the method of any one of claims 1-7.
10. A readable storage medium, characterized in that it stores thereon a program or instructions which, when executed by a processor, implement the steps of the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307492.XA CN115375205B (en) | 2022-10-25 | 2022-10-25 | Method, device and equipment for determining water user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307492.XA CN115375205B (en) | 2022-10-25 | 2022-10-25 | Method, device and equipment for determining water user portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115375205A true CN115375205A (en) | 2022-11-22 |
| CN115375205B CN115375205B (en) | 2023-06-23 |
Family
ID=84072735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211307492.XA Active CN115375205B (en) | 2022-10-25 | 2022-10-25 | Method, device and equipment for determining water user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375205B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050946A (en) * | 2023-03-29 | 2023-05-02 | 东莞先知大数据有限公司 | Water service user collection management method and device, electronic equipment and storage medium |
| CN116402260A (en) * | 2023-06-07 | 2023-07-07 | 埃睿迪信息技术（北京）有限公司 | Method, device and equipment for determining drainage household portrait |
| CN117851953A (en) * | 2024-02-22 | 2024-04-09 | 深圳拓安信物联股份有限公司 | Water use abnormality detection method, device, electronic apparatus, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764984A (en) * | 2018-05-17 | 2018-11-06 | 国网冀北电力有限公司电力科学研究院 | A kind of power consumer portrait construction method and system based on big data |
| CN109002996A (en) * | 2018-07-26 | 2018-12-14 | 珠海卓邦科技有限公司 | Methods of risk assessment and system based on water rate |
| CN110796354A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Enterprise electric charge recovery risk portrait method and system |
| US20200117675A1 (en) * | 2017-07-26 | 2020-04-16 | Beijing Sankuai Online Technology Co., Ltd. | Obtaining of Recommendation Information |
| CN111723257A (en) * | 2020-06-24 | 2020-09-29 | 山东建筑大学 | User portrait drawing method and system based on water usage law |
| CN115062087A (en) * | 2022-07-01 | 2022-09-16 | 国网汇通金财（北京）信息科技有限公司 | User portrait construction method, device, equipment and medium |
-
2022
- 2022-10-25 CN CN202211307492.XA patent/CN115375205B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200117675A1 (en) * | 2017-07-26 | 2020-04-16 | Beijing Sankuai Online Technology Co., Ltd. | Obtaining of Recommendation Information |
| CN108764984A (en) * | 2018-05-17 | 2018-11-06 | 国网冀北电力有限公司电力科学研究院 | A kind of power consumer portrait construction method and system based on big data |
| CN109002996A (en) * | 2018-07-26 | 2018-12-14 | 珠海卓邦科技有限公司 | Methods of risk assessment and system based on water rate |
| CN110796354A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Enterprise electric charge recovery risk portrait method and system |
| CN111723257A (en) * | 2020-06-24 | 2020-09-29 | 山东建筑大学 | User portrait drawing method and system based on water usage law |
| CN115062087A (en) * | 2022-07-01 | 2022-09-16 | 国网汇通金财（北京）信息科技有限公司 | User portrait construction method, device, equipment and medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050946A (en) * | 2023-03-29 | 2023-05-02 | 东莞先知大数据有限公司 | Water service user collection management method and device, electronic equipment and storage medium |
| CN116402260A (en) * | 2023-06-07 | 2023-07-07 | 埃睿迪信息技术（北京）有限公司 | Method, device and equipment for determining drainage household portrait |
| CN117851953A (en) * | 2024-02-22 | 2024-04-09 | 深圳拓安信物联股份有限公司 | Water use abnormality detection method, device, electronic apparatus, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115375205B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11398000B2 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN115375205A (en) | Method, device and equipment for determining water user portrait | |
| Xia et al. | Detection methods in smart meters for electricity thefts: A survey | |
| US11372896B2 (en) | Method and apparatus for grouping data records | |
| Nizar et al. | Power utility nontechnical loss analysis with extreme learning machine method | |
| CN105678398A (en) | Power load forecasting method based on big data technology, and research and application system based on method | |
| Montañez et al. | A machine learning approach for detecting unemployment using the smart metering infrastructure | |
| CN108492134A (en) | The big data user power utilization behavior analysis system integrated based on multicycle regression tree | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| Wang et al. | Short-term industrial load forecasting based on ensemble hidden Markov model | |
| CN109583729B (en) | Data processing method and device for platform online model | |
| Cho et al. | A Delphi technology forecasting approach using a semi-Markov concept | |
| CN113205223A (en) | Electric quantity prediction system and prediction method thereof | |
| CN112614004A (en) | Method and device for processing power utilization information | |
| CN113570398A (en) | Promotion data processing method, model training method, system and storage medium | |
| CN116823496A (en) | Intelligent insurance risk assessment and pricing system based on artificial intelligence | |
| CN110009427B (en) | Intelligent electric power sale amount prediction method based on deep circulation neural network | |
| Flesca et al. | On forecasting non-renewable energy production with uncertainty quantification: A case study of the Italian energy market | |
| Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
| CN111126629A (en) | Model generation method, system, device and medium for identifying brushing behavior | |
| CN113537607B (en) | Power failure prediction method | |
| Daraghmi et al. | Accurate and time‐efficient negative binomial linear model for electric load forecasting in IoE | |
| Buzau | Machine learning algorithms for the detection of non-technical losses in electrical distribution networks | |
| Pang et al. | Short-term power load forecasting based on gray relational analysis and support vector machine optimized by artificial bee colony algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wu Liyang Inventor after: Huang Tao Inventor before: Wu Liyang Inventor before: Huang Tao Inventor before: Liu Lifeng |
|
| CB03 | Change of inventor or designer information |